g-assismoraes/DeltaP2S-Qwen2.5-14B-SameFormula-Code-S13

TEXT GENERATIONPricing:Input $0.431 / Cached $0.0862 / Output $1.12Concurrent Unit Cost:1Model Size:14.8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 4, 2026Architecture:Transformer Featherless Exclusive Cold

DeltaP2S-Qwen2.5-14B-SameFormula-Code-S13 is a 14.8 billion parameter language model based on the Qwen2.5 architecture, specifically fine-tuned from Qwen/Qwen2.5-14B. This model is a product of the Qwen-aware Delta-P2S experiment package, indicating a specialized training approach. It is designed for tasks related to code, leveraging its Qwen2.5 foundation and a substantial 32768 token context length.

Loading preview...

Model Overview

This model, DeltaP2S-Qwen2.5-14B-SameFormula-Code-S13, is a 14.8 billion parameter language model derived from the Qwen2.5-14B base architecture. It was developed as part of the Qwen-aware Delta-P2S experiment package, suggesting a focused and experimental training methodology.

Key Characteristics

  • Base Model: Fine-tuned from Qwen/Qwen2.5-14B.
  • Parameter Count: 14.8 billion parameters, offering a balance of capability and computational requirements.
  • Context Length: Features a substantial 32768 token context window, enabling processing of longer inputs and generating more extensive outputs.
  • Training Origin: Produced through a specific training run identified as ./runs/codeqwen_SameFormula-S13/train/large_baseline, indicating a specialized training regimen.

Intended Use Cases

Given its origin from a "codeqwen" training run and the "SameFormula-Code" in its name, this model is likely optimized for:

  • Code Generation: Generating programming code snippets or full functions.
  • Code Understanding: Analyzing, explaining, or summarizing existing code.
  • Code Debugging: Assisting in identifying and suggesting fixes for code errors.
  • Software Development Tasks: General tasks within the software development lifecycle that benefit from a large language model with code-specific training.